Autonomous and Self-Adapting System for Synthetic Media Detection and Attribution

2025-04-04

AI Summary

Rapid advancements in generative AI have yielded increasingly photorealistic synthetic images, while existing detection systems—relying on static features—struggle to generalize to unseen generators. Method: We propose an autonomous, self-adaptive framework for synthetic image detection and provenance attribution that evolves alongside generative AI. Its core innovation is an open-set, self-evolving embedding space coupled with an unsupervised high-confidence clustering mechanism, enabling automatic discovery, representation learning, and incremental model fusion for unknown generators—without human annotation or intervention. Contribution/Results: The framework unifies real-time detection, attribution to known sources, and onboarding of novel sources. Evaluated across multiple generations of generative models, it achieves over 27% higher detection and attribution accuracy than state-of-the-art methods, significantly improving generalization and robustness.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

Rapid advances in generative AI have enabled the creation of highly realistic synthetic images, which, while beneficial in many domains, also pose serious risks in terms of disinformation, fraud, and other malicious applications. Current synthetic image identification systems are typically static, relying on feature representations learned from known generators; as new generative models emerge, these systems suffer from severe performance degradation. In this paper, we introduce the concept of an autonomous self-adaptive synthetic media identification system -- one that not only detects synthetic images and attributes them to known sources but also autonomously identifies and incorporates novel generators without human intervention. Our approach leverages an open-set identification strategy with an evolvable embedding space that distinguishes between known and unknown sources. By employing an unsupervised clustering method to aggregate unknown samples into high-confidence clusters and continuously refining its decision boundaries, our system maintains robust detection and attribution performance even as the generative landscape evolves. Extensive experiments demonstrate that our method significantly outperforms existing approaches, marking a crucial step toward universal, adaptable forensic systems in the era of rapidly advancing generative models.

Problem

• Detect synthetic images and attribute sources autonomously
• Adapt to new generative models without human intervention
• Maintain robust performance in evolving generative landscapes

Innovation

• Autonomous self-adaptive synthetic media identification system
• Open-set identification with evolvable embedding space
• Unsupervised clustering for continuous boundary refinement